Pinned Loading

1. inclusionAI/cuLA inclusionAI/cuLA Public

   CUDA kernels for linear attention variants, written in CuTe DSL and CUTLASS C++.

   Python 334 31

2. SandAI-org/MagiAttention SandAI-org/MagiAttention Public

   A Distributed Attention Towards Linear Scalability for Ultra-Long Context, Heterogeneous Data Training

   Python 763 45

3. sigmod-2024-contest sigmod-2024-contest Public

   🏆 The winner code for ACM SIGMOD 2024 Programming Contest. Efficient and Accurate Hybrid Vector Search

   C++ 9 1

4. flashinfer-ai/flashinfer flashinfer-ai/flashinfer Public

   FlashInfer: Kernel Library for LLM Serving

   Python 5.3k 868

5. tile-ai/tilelang tile-ai/tilelang Public

   Domain-specific language designed to streamline the development of high-performance GPU/CPU/Accelerators kernels

   Python 5.5k 497

6. vllm-project/vllm vllm-project/vllm Public

   A high-throughput and memory-efficient inference and serving engine for LLMs

   Python 75.4k 15.2k